Engrava runs on your own machine — the client starts it, so there is no endpoint to ping. 191 installs a week from pypi. Last commit 3 Oct 2026.
MindQL queries, hybrid search, and a thought graph - read/write memory for AI agents.
Today is the operative word: we check Engrava every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add engrava -e 'ENGRAVA_DB_PATH=<ENGRAVA_DB_PATH>' -- uvx engrava-mcp
{
"mcpServers": {
"engrava": {
"command": "uvx",
"args": [
"engrava-mcp"
],
"env": {
"ENGRAVA_DB_PATH": "<ENGRAVA_DB_PATH>"
}
}
}
}
[mcp_servers.engrava]
command = "uvx"
args = ["engrava-mcp"]
env = { ENGRAVA_DB_PATH = "<ENGRAVA_DB_PATH>" }
{
"mcpServers": {
"engrava": {
"command": "uvx",
"args": [
"engrava-mcp"
],
"env": {
"ENGRAVA_DB_PATH": "<ENGRAVA_DB_PATH>"
}
}
}
}
{
"servers": {
"engrava": {
"type": "stdio",
"command": "uvx",
"args": [
"engrava-mcp"
],
"env": {
"ENGRAVA_DB_PATH": "<ENGRAVA_DB_PATH>"
}
}
}
}
Put your own value in place of
<ENGRAVA_DB_PATH> (Absolute path to the SQLite database file. Created if missing; its directory must exist. Enough on its own: full-text search, the graph and MindQL work, but vector search needs ENGRAVA_MCP_CONFIG).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
ENGRAVA_MCP_CONFIG (Absolute path to an engrava.yaml, for an embedding provider (vector search) and the thought/edge journal. When set, it takes precedence and ENGRAVA_DB_PATH is not read), ENGRAVA_MCP_READ_ONLY (Set to true to register no write tools).
Local-first memory system for AI agents with hybrid search and graph reasoning
Graph memory that dreams: Neo4j knowledge-graph memory for AI agents with hybrid search
Persistent memory, hybrid search and a goal graph for AI agents, over stdio or remote HTTP.
Local memory server for AI agents: hybrid search, a fact graph and a hash-chained audit log.
Self-hosted persistent memory for AI agents: knowledge graph and hybrid search.
Semantic memory for AI agents with hybrid search, knowledge graph, and consolidation
Git-backed org memory for AI agents — hybrid search, tables, files & a URI graph over MCP.
Persistent memory for AI agents: Markdown entries, hybrid search, typed graph links
Answers built from our own checks of this server.